Icelandic ModernBERT warm-start study: ws-S-xl-s0, 80 tokens/parameter

Paper: Beyond IceBERT: Open-Data ModernBERT Encoders for Icelandic from 12M to 1B Parameters (arXiv:2610.36230). If you use this model, please cite the paper. The BibTeX entry is at the end of this card.

Question this run answers. Does a warm start still pay off for an Icelandic encoder, from which source model, and how many Icelandic tokens does it save? IceBERT (Snæbjarnarson et al., LREC 2022) found that continuing a multilingual model "can lead to state-of-the-art results for some downstream tasks". Our size ladder uses the Ettin shapes, so every size has an English Ettin encoder of identical shape (and base has mmBERT-base), and a warm start changes only the starting weights: architecture, data, tokenizer, schedule and evaluation stay those of the scratch models. Every arm is trained at 10, 20, 40 and 80 Icelandic tokens per parameter.

This model is the scratch arm: random initialisation, the scratch ladder's recipe unchanged, size xl, pretraining seed 0, at 80 tokens per parameter. This is the curve's main run to 80 tokens per parameter. It kept its state at the start of each shorter budget's decay phase, and the branches b10, b20 and b40 of this repo continue from those states.

Release. Released under the MIT licence with the paper; the training corpus is not released, because not every source states a licence that permits redistribution. In the paper this arm is called Scratch (the repo names keep the code names S, E, Erand, Mswap and Mkeep). Parts of the training data require attribution (CC BY 4.0: IGC; CC BY-SA: Wikipedia, Wikisource) or come from web crawls with mixed rights (IC3-v2 states no licence). MIM-GOLD and MIM-GOLD-NER, used only for evaluation, are licensed for research use, so no model fine-tuned on them is released.

Model

Fill-mask. Write the mask token right after the previous word, with no space: Reykjavík er höfuðborg[MASK]. The tokenizer keeps each word's leading space inside the word's token, so a space typed before the mask becomes a token of its own. In training such a lone space comes mostly before a number, because digits are split off, so with the space the model predicts digits.

Training

Results

Held-out MLM loss (15% masking) per source at the end of training: {"dynaword": 0.341, "finepdfs": 0.943, "fineweb2": 0.827, "hplt3": 0.839, "ic3v2": 0.551, "igc": 0.591, "macocu": 0.773, "madlad": 0.702, "wiki": 0.407}.

Downstream point of this arm, size and budget (x100). Each point pools the arm's pretraining seeds at this size (so it is not this checkpoint alone at xs, s and m) and 3-5 fine-tuning seeds at the learning rate the 80-point model chose on dev. 95% CIs are a hierarchical bootstrap over pretraining seeds, fine-tuning seeds and test items; differences are paired over the same item draws. "Scratch at 160" is the ladder's model trained on twice the 80-point tokens (it also saw CulturaX's unique remainder, +3.7%).

IceBERT's benchmarks and the added tasks (v2 protocol: learning-rate grids extended until the choice is interior; five fine-tuning seeds; PoS over the ten MIM-GOLD folds):

Caveats

• One pretraining seed at base, large and xl (1B); the CIs cover fine-tuning and test-item noise only.
• Branches reuse the fine-tuning learning rate chosen for the 80-point model of the same arm and size.
• At 1B the scratch branches at 10, 20 and 40 tokens per parameter were trained after the rest of the study (23 Oct 2026), from the scratch run's kept stable-phase states.
• Fine-tuning used bf16 autocast; parsers fall back to fp32 on non-finite losses.

Full numbers: the paper, arXiv:2610.36230.

Citation

@misc{einarsson2026icebertopendatamodernbertencoders,
  title         = {Beyond {IceBERT}: Open-Data {ModernBERT} Encoders for {Icelandic} from {12M} to {1B} Parameters},
  author        = {Hafsteinn Einarsson},
  year          = {2026},
  eprint        = {2610.36230},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2610.36230}
}